Repository
deepklarity/harness-kit agent skills
- skills
- 18
- GitHub stars
- 100
GitHub description: “A kit for building with AI agents and also the engineering patterns around it. ”
- Stars
- 100 (13 forks)
- Licence
- MIT
- Last push
- Jul 2026
- Created
- Mar 2026
- agent-skills
- agentic-ai
- agentic-framework
- harness-engineering
Install all skills
npx skills add deepklarity/harness-kitAdd --skill <name> for a single skill and -a <agent> to choose the agent (see the agent guides).
Skills in deepklarity/harness-kit, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Create new skills, modify and improve existing skills, and measure skill performance. | deepklarity/ | 100 | — | ~3.2k | Automated safety check: Notes | MIT | 2 mo ago |
| 2 | Run comprehensive agent-native architecture review with scored principles. | deepklarity/ | 100 | — | ~1.1k | Automated safety check: Notes | MIT | 2 mo ago |
| 3 | Mock-first, layer-by-layer feature development. An agent skill from deepklarity/harness-kit. | deepklarity/ | 100 | — | ~3.9k | Automated safety check: Notes | MIT | 2 mo ago |
| 4 | Audit whether an AI agent can autonomously close the loop on problems in a given area — from discovering a symptom to verifying a fix — without human intervention. | deepklarity/ | 100 | — | ~2.5k | Automated safety check: Notes | MIT | 2 mo ago |
| 5 | Traces a workflow end-to-end through the harness-kit monorepo and creates a breadcrumb analysis doc in docs/breadcrumbanalysis/. | deepklarity/ | 100 | — | ~3k | Automated safety check: Notes | MIT | 2 mo ago |
| 6 | Generate changelog entries from git diffs, prepend to CHANGELOG.md, and optionally commit + PR. | deepklarity/ | 100 | — | ~1.6k | Automated safety check: Notes | MIT | 2 mo ago |
| 7 | Compound a learning into a reusable pattern. An agent skill from deepklarity/harness-kit. | deepklarity/ | 100 | — | ~1.7k | Automated safety check: Notes | MIT | 2 mo ago |
| 8 | Consults existing breadcrumb analysis docs before exploring the codebase. | deepklarity/ | 100 | — | ~1.4k | Automated safety check: Notes | MIT | 2 mo ago |
| 9 | Run diagnostic scripts on tasks, specs, boards, or reflections. | deepklarity/ | 100 | — | ~808 | Automated safety check: Notes | MIT | 2 mo ago |
| 10 | Inspect and debug errors via logs across the harness-kit monorepo. | deepklarity/ | 100 | — | ~2.1k | Automated safety check: Notes | MIT | 2 mo ago |
| 11 | Plan and execute an odin spec. An agent skill from deepklarity/harness-kit. | deepklarity/ | 100 | — | ~924 | Automated safety check: Notes | MIT | 2 mo ago |
| 12 | Resolve merge conflicts in the current branch. An agent skill from deepklarity/harness-kit. | deepklarity/ | 100 | — | ~2.2k | Automated safety check: Notes | MIT | 2 mo ago |
| 13 | 13.Hk Rca Interactive Root Cause Analysis enforcer. An agent skill from deepklarity/harness-kit. | deepklarity/ | 100 | — | ~1.5k | Automated safety check: Notes | MIT | 2 mo ago |
| 14 | 14.Hk Refine Iteratively improve any output by running a structured observe-hypothesize-change-rerun loop. | deepklarity/ | 100 | — | ~2.4k | Automated safety check: Notes | MIT | 2 mo ago |
| 15 | Run a scout wave over outside sources (links, blogs, trending repos) into a progressive-disclosure research wiki in the current project, then distill findings into the project's ideas/backlog file. | deepklarity/ | 100 | — | ~885 | Automated safety check: Pass | MIT | 2 mo ago |
| 16 | Run a codebase hygiene audit. An agent skill from deepklarity/harness-kit. | deepklarity/ | 100 | — | ~1.2k | Automated safety check: Notes | MIT | 2 mo ago |
| 17 | Create and maintain a shift-handover HTML changelog artifact — a page the returning human reads in two minutes to know everything that happened while they were away. | deepklarity/ | 100 | — | ~867 | Automated safety check: Pass | MIT | 2 mo ago |
| 18 | 18.Fable Audit Audit the fable roadmap (docs/fableroadmap/) — verify claimed progress with proof, write a short report, update RESUME state + BACKLOG rank. | deepklarity/ | 100 | — | ~582 | Automated safety check: Notes | MIT | 2 mo ago |
Questions, answered from the data.
What is the best skill in deepklarity/harness-kit?
Hk Skill Creator from deepklarity/harness-kit ranks first of the 18 skills in deepklarity/harness-kit listed here, with the highest score: its repository has 100 GitHub stars, its SKILL.md loads about 3.2k tokens and it has informational notes only in the automated safety check. Next come Hk Arch Audit and Hk Mock First.
Are the skills in deepklarity/harness-kit official?
None yet. All 18 skills in deepklarity/harness-kit listed here come from community repositories; a skill counts as official when the product's own GitHub organization publishes it.
How do I install all skills from deepklarity/harness-kit?
Run npx skills add deepklarity/harness-kit in your project: the open-source skills CLI installs the repository's skills into your coding agent's skills folder. To install a single skill, open its page here for the exact command.
How are these skills ranked?
By Skill Navigator score, which combines the GitHub stars of the skill's repository (shared across that repo's skills and discounted for large collections), how many other GitHub owners carry a copy of the skill, and automated SKILL.md quality checks, minus penalties for safety-check warnings and for each further skill from the same repository. Skills that fail the safety check are not listed.